• Publications
  • Influence
Recognition of Faux Pas by Normally Developing Children and Children with Asperger Syndrome or High-Functioning Autism
Most theory of mind (ToM) tests are designed for subjects with a mental age of 4–6 years. There are very few ToM tests for subjects who are older or more able than this. We report a new test of ToM,Expand
  • 879
  • 77
  • PDF
Beyond the session timeout: automatic hierarchical segmentation of search topics in query logs
TLDR
This is the first work to identify, measure and automatically segment sequences of user queries into their hierarchical structure. Expand
  • 446
  • 46
  • PDF
Temporal profiles of queries
TLDR
Documents with timestamps, such as email and news, can be placed along a timeline. Expand
  • 222
  • 43
  • PDF
Generating query substitutions
TLDR
We introduce the notion of query substitution, that is, generating a new query to replace a user's original search query. Expand
  • 683
  • 32
  • PDF
Learning Dictionaries for Information Extraction by Multi-Level Bootstrapping
TLDR
We present a multilevel bootstrapping algorithm that generates both the semantic lexicon and extraction patterns simultaneously. Expand
  • 865
  • 31
  • PDF
Information re-retrieval: repeat queries in Yahoo's logs
TLDR
This paper explores repeat search behavior through the analysis of a one-year Web query log of 114 anonymous users and a separate controlled survey of an additional 119 volunteers. Expand
  • 324
  • 19
  • PDF
Beyond DCG: user behavior as a predictor of a successful search
TLDR
We show that user behavior alone can give an accurate picture of the success of the user's web search goals, without considering the relevance of the documents displayed. Expand
  • 218
  • 19
  • PDF
Predicting searcher frustration
TLDR
We present several models to predict searcher frustration using features extracted from query logs and physical sensors. Expand
  • 154
  • 16
  • PDF
Active Learning with Feedback on Features and Instances
TLDR
We extend the traditional active learning framework to include feedback on features in addition to labeling instances, and we execute a careful study of the effects of feature selection and human feedback onfeatures in the setting of text categorization. Expand
  • 200
  • 14
Automatic Online Evaluation of Intelligent Assistants
TLDR
We use implicit feedback from users to predict whether users are satisfied with the intelligent assistant as well as its components, i.e., speech recognition and intent classification. Expand
  • 102
  • 12
  • PDF